Charles Campbell Roberts Profile picture
Sep 24, 2020 14 tweets 8 min read Read on X
Rapid whole genome (🧬) sequencing (rWGS) is one of the most exciting (and benevolent) collisions of #AI and #genomics I can think of.

rWGS can diagnose a critically ill child in minutes where previously it took years.

illumina.com/company/news-c…
A few years ago, Illumina ($ILMN) and Rady Children's Hospital (@RadyGenomics) collaborated to offer sequencing services for diagnosing critically-ill infants and toddlers.

Roughly 70% of rare diseases are genetic and they can take five years to diagnose.
As sequencing costs dropped and #AI got faster, this collaboration became Project Baby Bear: a pilot study for rWGS's diagnostic yield, clinical utility, and health economics in practice.

Several innovative companies joined Rady's in creating a rapid diagnostic pipeline.
@Clinithink contributed a natural language processing (#NLP) system to scour medical literature and the patient's EHR. Traditionally, this process would be carried out manually.

clinithink.com/life-science
Genomic data would be fed to Diploid's (@diploidgenomics) AI-engine, MOON, which can suggest a causal #DNA variant out of ~45 million in just about five minutes.

This result would be verified on Fabric Enterprise; software by @FabricGenomics.

diploid.com/moon
After the pilot, Rady's rWGS was covered by Blue Shield of California (~$5,000).

Resurfacing, @ARKInvest believes #AI-accelerated #genomic diagnostics should be less expensive and more accessible in local hospitals. You shouldn't need to travel to receive the best care.
So, where can we go from here?

A 2019 @AJHGNews article noted that the rare disease solve rate was <50% when using short read rWGS. The authors argued this rate could increase on long read systems given their ability to decipher hard-to-read variants.

nature.com/articles/s1003…
For visual learners, @PacBio has a webinar on this topic (tinyurl.com/y3ly77hg).

Interestingly, Pacific Biosciences and Leiden University (@LUMC_Leiden), another hospital using Diploid's MOON, have a long-read/diagnostic summit series called SMRT Leiden.
Earlier this year, Invitae (@Invitae) acquired Diploid to (a) accelerate and lower the cost of its whole exome/genome services and (b) to democratize access to MOON for children's hospitals of all sizes.

ir.invitae.com/news-and-event…
Given the lower CapEx of PacBio sequencers and cost-declines associated w/ compute, we think some centers could profitably integrate decentralized long-read rWGS services, analyzable over the cloud w/ MOON.

Others have the flexibility to send samples to Invitae's central lab.
Moreover, we think Invitae's integration of genetic counseling AI / clinical workflow management tools (@cleargenetics), investments in telemedicine integration, and focus on rationalizing price, could galvanize rWGS adoption.

ir.invitae.com/news-and-event…
Altogether, rWGS is one of the most benevolent, impactful collisions of different areas of innovation and collaboration among various companies. #NGS #AI
NOTE:

A lab/hospital using PacBio, or another long-read platform, would need an LDT/certification to use such a system for diagnostic purposes as none currently are FDA cleared/CE-marked for diagnostic purposes.

• • •

Missing some Tweet in this thread? You can try to force a refresh
 

Keep Current with Charles Campbell Roberts

Charles Campbell Roberts Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @CCRobertsARK

Jan 5, 2023
>90% of Americans over 45 have seen a Cologuard ad this week.

Fewer know of the test's parent company, Exact Sciences (EXAS), whose tests also guide care for the majority of early-stage breast cancer patients in the US.

Today, we released a 5-year model + article on Exact.
Our (base case) 2027 price target is $140 ($49 today). To get there, here's what we believe has to happen:

1. Exact's core business (Cologuard + Oncotype DX) grows on avg. >15% per year thru 2027, reaching $4B.

2. Exact achieves EBITDA positivity in the '23/'24 timeframe.
What we believe must happen (Cont.):

3. Exact uses its earnings to reinvest in its burgeoning pipeline, service its outstanding debt, and maintain its capital equipment.

4. Exact's pipeline, in aggregate, hits >$1B revenue by the end of 2027.

How does the model work?
Read 19 tweets
Jun 16, 2022
The following paper is one of the most interesting and thoughtful I've read in quite some time.

The authors offer a new framework for understanding if genetic mutations are harmless (benign) or dangerous (pathogenic).

Spoiler: AlphaFold 2 is involved.

nature.com/articles/s4146…
First, I'd like to cite the authors; .@capra_lab, .@rodendm, and .@computbiolgeek. I'm sure they'll correct me if I butcher anything.

I originally stumbled on the paper after reading a thread about it by .@RyanDhindsa, which I've linked below:

Some Background:

The basis of medical genetics is understanding how #DNA mutations (variants) give rise to disease.

Recall that inherited DNA sequence variants can sometimes alter proteins by changing the identity of an amino acid.

This is called a 'missense mutation'. Image
Read 23 tweets
Jan 18, 2022
Now that @Quantum_Si has given us a peek under the hood of its protein #sequencing platform (Platinum), we can begin comparing actual results to theory.

A few months ago, I shared this paper that gave a theoretical framework for protein sequencing:
pubs.acs.org/doi/10.1021/ac…
The author simulated how different factors, such as the # of readable amino acids (AAs) and the read length, would affect a protein sequencer's ability to unambiguously detect the 20,000 canonical human proteins in our bodies.

That chart is attached below.
I've marked in green where QSI currently stacks up. Based on its recent pre-print (linked below), Platinum can directly read seven (7) amino acids (F, Y, W, L, I, V, and R) with peptide reads that seem to max out around 20 AAs.

biorxiv.org/content/10.110…
Read 10 tweets
Dec 16, 2021
A recent publication by Dennis Lo et al applied long-read sequencing (LRS) in the prenatal screening (#NIPT) setting. It's a rather unorthodox technology/application pairing, and it's got me scratching my head a bit.

Open Acces Link:

pnas.org/content/118/50…
For context, earlier this year, Lo et al published a convolutional neural network ("the HK model") that enabled PacBio LRS devices to read methylation (5mC) across the entire genome with very high fidelity. This is important later.

What's methylation?
PDF of HK Model Paper:
pnas.org/content/pnas/1…

I'll summarize my main takeaways from the current paper and end with some of my open questions/concerns.
Read 30 tweets
Dec 3, 2021
@MJLBio @Sanctuary_Bio @Biohazard3737 Sure! I realize I was being a little vague with those statements. Generally, I think you're correct in your interpretation of the importance of P2 (great $/GB, but at a smaller scale) as well as duplex sequencing.

Something that is important to recognize, though ...
@MJLBio @Sanctuary_Bio @Biohazard3737 ... is how product deployment works differently between PacBio and Nanopore, which is partly an artefact of culture and of time in the public markets, in the public markets. I'm not advocating for one over the other with my next statements.
@MJLBio @Sanctuary_Bio @Biohazard3737 PacBio has been a public company for a long time. While the management has changed much since the failed Illumina merger, the familiarity with how to operate as a public company has not.

PacBio is more secretive and only unveils fully built-out commercial products.
Read 5 tweets
Sep 16, 2021
I'd like to share my initial reaction to today's Berkeley Lights report. But first, I need to do some housekeeping. I can't comment on stock movements, share financial projections, or debate fair value.

Please see our general disclosure: ark-invest.com/terms/#twitter
Generally, I respect anyone who's put this much work into a topic. I won't pretend to have a clean rebuttal to every point. In my experience, beyond the hyperbole and hasty generalizations, there is some truth in these types of reports.

I want to soberly appraise those truths.
Also, I'd invite the subject-matter experts waiting in the wings to build off of this thread, add detail, or share their experiences. Ultimately, we're all after the same thing.

I will start with a few concessions and end with a few counterpoints to today's report:
Read 28 tweets

Did Thread Reader help you today?

Support us! We are indie developers!


This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Don't want to be a Premium member but still want to support us?

Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us!

:(